Update README.md

README.md

@@ -4,7 +4,7 @@ Source code for [Offline Reinforcement Learning for LLM Multi-Step Reasoning](ht
 
 Model: [Policy](https://huggingface.co/jwhj/Qwen2.5-Math-1.5B-OREO) | [Value](https://huggingface.co/jwhj/Qwen2.5-Math-1.5B-OREO-Value)
 
-<img src="./OREO.png" alt="Image description" width="50%" />
+<img src="https://raw.githubusercontent.com/jwhj/OREO/refs/heads/main/OREO.png" alt="Image description" width="50%" />
 
 
 # Installation